Structured inference networks for nonlinear state space models

Rahul G. Krishnan, Uri Shalit, David Sontag

Research output: Contribution to conferencePaper

Abstract

Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.

Original languageEnglish (US)
Pages2101-2109
Number of pages9
StatePublished - 2017
Event31st AAAI Conference on Artificial Intelligence, AAAI 2017 - San Francisco, United States
Duration: Feb 4 2017Feb 10 2017

Other

Other31st AAAI Conference on Artificial Intelligence, AAAI 2017
CountryUnited States
CitySan Francisco
Period2/4/172/10/17

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Structured inference networks for nonlinear state space models'. Together they form a unique fingerprint.

  • Cite this

    Krishnan, R. G., Shalit, U., & Sontag, D. (2017). Structured inference networks for nonlinear state space models. 2101-2109. Paper presented at 31st AAAI Conference on Artificial Intelligence, AAAI 2017, San Francisco, United States.